Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 668 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.8140. Min Act: -0.1700
Data Index: 1440685 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.7828. Min Act: -0.1700
Data Index: 1778744 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.7515. Min Act: -0.1700
Data Index: 672008 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.7828. Min Act: -0.1700
Data Index: 6617942 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.7515. Min Act: -0.1700
Data Index: 4130432 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.7203. Min Act: -0.1700
Data Index: 5016921 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6890. Min Act: -0.1700
Data Index: 986948 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6890. Min Act: -0.1700
Data Index: 1673764 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6890. Min Act: -0.1700
Data Index: 5413946 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6578. Min Act: -0.1700
Data Index: 2340467 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6265. Min Act: -0.1700
Data Index: 7194328 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6265. Min Act: -0.1700
Data Index: 7011135 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6578. Min Act: -0.1700
Data Index: 6165789 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6578. Min Act: -0.1700
Data Index: 2609661 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6265. Min Act: -0.1700
Data Index: 4299147 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.6578. Min Act: -0.1700
Data Index: 3547027 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.5953. Min Act: -0.1700
Data Index: 6424567 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.5953. Min Act: -0.1700
Data Index: 6734272 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.5953. Min Act: -0.1700
Data Index: 5643224 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8140. Min Range: -4.8140
Max Act: 4.5640. Min Act: -0.1700
Data Index: 7965291 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19